© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14594
    Prev
    Next
    INDEX
    Explanations

    references to data organization and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fourteen
    -0.57
    تقاوى
    -0.49
     Sixteen
    -0.47
    httphttps
    -0.46
     beider
    -0.45
     Infórmanos
    -0.44
     begge
    -0.42
    Twenty
    -0.41
     dizaines
    -0.40
    几十
    -0.39
    POSITIVE LOGITS
     three
    2.27
    three
    2.03
     trio
    1.99
    Three
    1.91
     Three
    1.90
     üç
    1.82
     trois
    1.81
    三
    1.72
     drei
    1.70
    THREE
    1.70
    Activations Density 1.241%

    No Known Activations